Fingerprint verification using haar wavelet

This paper deals with a new image based approach for fingerprint verification using Haar Wavelet Transform. Haar wavelet is used for decomposition of the fingerprint image. Haar wavelet transformation is carried out directly on the gray-scaled fingerprint image without any preprocessing steps. Decomposition of the fingerprint image is carried out up to three levels. Then wavelet statistical features are extracted from decomposed fingerprint image. This wavelet based approach verifies the unknown fingerprint image with stored enrolled fingerprint images by using distance vector formula with better verification rate. Database used is of Biolab, University of Bologna. For training, fingerprint images of sixty subjects are taken from database and training time is 29 sec. Fingerprint verification is done with a total of 2160 fingerprint images obtained by rotating each of the fingerprint of sixty subjects from 0° to 360° in steps of 10° each. It requires 1 msec for verification of one fingerprint image. Experimental results shows better overall success percentage rate 82.08 for fingerprint verification based on haar wavelet transform with False Acceptance Rate 0.5.